zhuiganfa

模拟退火算法的基本思想是从一给定解开始,从邻域中随机产生另一个解,接受Metropolis准则允许目标函数在有限范围内变坏,它由一控制参数t决定,其作用类似于物理过程中的温度T,对于控制参数的每一取值,算法持续进行“产生—判断—接受或舍去”的迭代过程,对应着固体在某一恒定温度下的趋于热平衡的过程,当控制参数逐渐减小并趋于0时,系统越来越趋于平衡态,最后系统状态对应于优化问题的全局最优解,该过程也称为冷却过程,由于固体退火必须缓慢降温,才能使固体在每一温度下都达到热平衡,最终趋于平衡状态,因此控制参数t经缓慢衰减,才能确保模拟退火算法最终优化问题的整体最优解。(Simulated annealing algorithm based on the idea that a given solution from the beginning, randomly generated from the adjacent domain to another solution, Metropolis acceptance criteria for the objective function to allow a limited range of deterioration, which is a control parameter t decided that its role is similar to the physical the course of the temperature T, the control parameters for each value, the algorithm continued to "have- to determine- to accept or rounding" of the iterative process, corresponding to a solid at a constant temperature of the process tends to thermal equilibrium, when control parameters and tended to decrease gradually 0:00, the system equilibrium state more and more, and finally the system state corresponds to the optimization problem of global optimal solution, the process is also known as the cooling process must be slow as a result of annealing temperature of solid to make solid temperature in each of them had attained thermal equilibrium, and ultim)

说明：  matlab编写的动态跟踪程序，可用USB摄像头来实现(Dynamic tracking program written in matlab)

利用SVM做回归线性测试。对于大盘指数的有效预测可以从整体上观测股市的变化提供强有力的信息，所以对上证指数的预测很有意义。通过对上证指数从1990.12.20-2009.08.19每日的开盘数进行回归分析，最终拟合的结果是：均方误差MSE=2.35705 e-005，平方相关系数 R=99.9195 。SVM的拟合结果还是比较理想的。(Make use of SVM linear regression testing. For the market index can predict the observed changes in the stock market as a whole to provide a strong information, so it makes sense to predict the Shanghai index. Through the Shanghai Composite Index opened daily from 1990.12.20-2009.08.19 number of regression analysis, the results of the final fit are: mean square error MSE = 2.35705 e-005, the square of the correlation coefficient R = 99.9195 . SVM fitting result is quite satisfactory.)

说明：  蚁群算法 matlab程序，已运行，很好用奥(Ant colony algorithm is already running and matlab, very good)

说明：  产生高斯白噪声，使用matlab编辑及仿真，均值为零(have a Gaussian white noise, editing and the use of Matlab simulation, mean zero)

（1） 本系统用到四种神经网络对漏电嫌疑系数进行预测，分别是BP神经网络、RBF神经网络、GRNN神经网络、Elman神经网络，通过对神经网络结构参数的设置和调试，可以得到很好的预测效果，实际值和预测值之间的误差能达到5 以内。 （2） 本系统使用matlab做GUI界面，在界面上就可以分别对这四种神经网络的结构参数进行设置，从而可以调整神经网络的结构，达到较好的预测精度。 ((1) The system used four neural network to predict the suspected leakage coefficient, respectively, the BP neural network, RBF neural network, GRNN neural network, Elman neural network, the neural network structure parameter setting and commissioning, can get very good prediction, between the actual and predicted values ​ ​ of error of less than 5 . (2) the use matlab to do the GUI interface, the interface can each of these four neural network structure parameters set, the structure of the neural network, which can be adjusted to achieve better prediction accuracy.)

快速中值滤波，在大数据量的情况下速度很快，论文“Median Filter in Constant Time”的C语言实现(C souce code for "Median Filter in Constant Time")

相控阵天线的方向图（切比雪夫加权），DC-DC部分采用定功率单环控制，esprit算法对有干扰的信号频率进行估计。( Phased array antenna pattern (Chebyshev weights), DC-DC power single-part set-loop control, esprit algorithm signal frequency interference can be assesse.)

说明：  多传感器融合算法，可以将多传感器的数据经处理，相比单传感器数据更加有效(Multi sensor fusion algorithm can process multi-sensor data, which is more effective than single sensor data)

智能控制第二版刘金琨著。 本书较全面地叙述了智能控制的基本理论、方法和应用。此代码为次数的附带程序。(Intelligent Control Second Edition was written by Liu Jin_Kun. This book describes more fully the intelligent control of the basic theory, methods and applications. This code is the number of accompanying program.)